© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 83048
    Prev
    Next
    INDEX
    Explanations

    terms related to data mutations in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    微软éĽħé»ij
    -0.07
    /shop
    -0.06
    porn
    -0.06
    :"-"`↵
    -0.06
     threaten
    -0.06
    -addons
    -0.06
    surf
    -0.06
    ease
    -0.06
    ding
    -0.06
    uchs
    -0.06
    POSITIVE LOGITS
    ights
    0.08
    amber
    0.08
    \Migration
    0.07
    ÑĤаж
    0.07
    uncios
    0.07
     ()->
    0.06
    -fontawesome
    0.06
    aland
    0.06
    ounge
    0.06
    ambre
    0.06
    Activations Density 0.000%

    No Known Activations